作者: J. Thomas Ngo , Joe Marks
关键词: Genetic algorithm 、 Graphics 、 Computer graphics 、 Search algorithm 、 Cultural algorithm 、 Evolutionary computation 、 Animation 、 Theoretical computer science 、 Computer science 、 Genetic representation
摘要: The Spacetime Constraints (SC) paradigm, whereby the animator specifies what an animated figure should do but not how to it, is a very appealing approach animation. However, algorithms available for realizing SC are limited. Current techniques local in nature: they all use some kind of perturbational analysis refine initial trajectory. We propose global search algorithm that capable generating multiple novel trajectories problems from scratch. key elements our strategy method encoding as behaviors, and genetic choosing behavior parameters currently implemented on massively parallel computer. describe show computed solutions 2D articulated figures. CR Categories: I.2.6 [Artificial Intelligence]: Learning— parameter learning. Problem Solving, Control Methods Search—heuristic methods. I.3.7 [Computer Graphics]: Three-Dimensional Graphics Realism— I.6.3 [Simulation Modeling]: Applications. Additional